Control Chart for

Variables

(Mean & Range

Charts)
We will Discuss…..
• Introduction
• Variability
• Acceptance Sampling
• Statistical Process Control
• Control Charts
• Mean Charts
• Range Charts
• Interpreting Control Charts
• Process Capability
Control Chart for
Variables
Control Chart for Variables
• The fundamental tool in SPC is the Control Charts

• Used to assess and distinguish sources of variability

• Control Charts is the visual depiction of quality

measurements from the samples taken from a
process, with multiple samples taken over time
Control Chart for Variables
• For Example,

• Imagine a bottling process in a soft drink plant

• Variable of interest shall be filling level

• The amount of soft drink in each bottle – for which a

narrow set of tolerances is set

• Samples are taken at a regular interval

Control Chart for Variables
• An SPC typically relies on two control charts for variables:

• Mean Charts (Show Process Averages)

• Range Charts (Show Process Dispersion)

• Together, they indicate whether a process is in control

• They should always be used together, because they provide

different information about process stability
The Mean Chart
• It is also known as x-bar chart

• The mean chart captures averages from a series of samples

• It is sequential (time-ordered) plot of the sample means

• For example : For a soft drink bottle filling line, if we

measure the average volume of liquid in each bottle in a
series of samples, we can chart the sample means
 Sample Obs. 1 Obs. 2 Obs. 3 Obs. 4 Obs. 5 X-Bar R-Bar
1 12.03 12.05 11.92 11.91 12.01 11.98 0.14
2 12.09 12.11 11.94 11.99 12.05 12.04 0.17
3 11.87 12.02 12.06 12.08 12.00 12.01 0.21
4 12.04 11.93 11.96 11.90 11.98 11.96 0.14
5 11.99 12.02 12.00 11.97 12.05 12.01 0.08
6 11.92 11.87 12.02 12.03 11.98 11.96 0.16
7 12.12 12.09 11.98 11.96 12.02 12.03 0.16
8 12.10 12.11 12.03 11.99 11.98 12.04 0.13

Sample 9
10
11.87
12.11
11.95
12.04
12.04
12.01
12.00
11.95
11.97
12.02
11.97
12.03
0.17
0.16

Measurements 11
12
12.01
11.98
11.96
11.96
11.87
12.01
11.97
12.05
12.03
12.00
11.97
12.00
0.16
0.09

from Soft Drink 13

14
12.04
11.98
11.93
11.96
11.99
11.90
12.01
12.05
12.05
11.99
12.00
11.98
0.12
0.15
Filling Line 15
16
12.10
12.08
12.07
11.93
11.96
12.06
12.02
11.98
12.03
12.01
12.04
12.01
0.14
0.15
17 11.92 12.11 11.96 11.97 11.99 11.99 0.19
18 12.07 12.09 11.99 12.10 12.00 12.05 0.11
19 12.05 12.01 11.94 11.98 11.92 11.98 0.13
20 11.99 12.07 12.05 12.09 12.01 12.04 0.10
21 12.11 12.04 11.99 11.97 12.04 12.03 0.14
22 11.93 11.99 12.01 11.95 11.98 11.97 0.08
23 11.97 12.05 12.08 11.99 12.00 12.02 0.11
24 12.06 12.04 12.05 11.99 11.97 12.02 0.09
25 11.92 11.99 12.01 11.96 11.93 11.96 0.09
12.00 0.13
Sample Means from Soft Drink-Filling Line
UCL & LCL for Mean Chart
Because the sample means are distributed according to a
normal distribution, we can use standard deviation to define
upper and lower limits which are called as Control Limits
Common Z Values

• Setting Z : The acceptable number of standard

deviations

• Central limit theorem guarantees that the sample

mean fit a normal distribution

• The Z- Value and the % between the control limits

are known exactly
Common Z Values

• It is common practice to use 3

(Three) standard deviations

• Which means 99.73% of the

sample means will fall between
UCL & LCL if the process is stable
Another Approach for Finding LCL
& UCL
• The Standard Deviation of Sample Means
▪ can be reasonably estimated from historical data
▪ if the sample sizes are large enough

• When this data is not available, or sample sizes are small

▪ another approach is to use a well-established relationship
between
▪ the range of a sample (R equals the largest value minus the
smallest value in the sample)
Another Approach for Finding LCL
& UCL
• The random variable w=R/𝞂 is called the relative range,
where 𝞂 is standard deviation

• Its distribution depends on the

• sample size n, and its mean is denoted d 2
▪ An estimator for the standard deviation of the sample
means, s, is
Another Approach for Finding LCL &
UCL
Mean Chart for Samples from Soft Drink-Filling Line
Mean Charts for Two Processes
Mean Charts for Two Soft Drink-Filling
Lines
 The Range Chart
• Like Standard deviation, the range of a sample is a measure of its
dispersion around the mean – that is, a measure of its variability
• Traditionally Range was used rather than standard deviation as it
could easily be calculated by workers

d2 and d3 are function of n (sample size)

The Range Chart
Range Chart for Samples from
Soft Drink -Filling Line
The Mean & Range
Charts
The Mean Chart & Range Chart
• The Mean Chart and Range Chart must be viewed
together
• Mean Chart
• Reflects the “Central Tendency”
• Shows any changes in the averages across the samples
• Range Chart
• Measures Dispersion or “Spread” within each sample

Neither Chart on it own is sufficient to determine if a process is in control

Stylized Control Charts for Two Different
Processes

Both processes are out of control but in different ways

Target Shooting Results
Control Charts for Factory
• Control Chart tells us if the
process is STABLE
• It rings an alarm bell that –
Something has happened
• Control Charts are likely
indicators of future problem
• We need to dig further to
understand the root cause

• The sample points outside

the control limits indicate the
process is out of control
Use of MS Excel to draw
mean and range charts
We have Discussed…..
• Introduction
• Variability
• Acceptance Sampling
• Statistical Process Control
• Control Charts
• Mean Charts
• Range Charts
• Interpreting Control Charts
• Process Capability